Linear combinations of primitives in vertebrate motor control.
نویسندگان
چکیده
منابع مشابه
Linear combinations of primitives in vertebrate motor control.
Recent investigations on the spinalized frog have provided evidence suggesting that the neural circuits in the spinal cord are organized into a number of distinct functional modules. We have investigated the rule that governs the coactivation of two such modules. To this end, we have developed an experimental paradigm that involves the simultaneous stimulation of two sites in the frog's spinal ...
متن کاملLearning Prioritized Control of Motor Primitives
Many tasks in robotics can be decomposed into sub-tasks that are performed simultaneously. In many cases, these sub-tasks cannot all be achieved jointly and a prioritization of such sub-tasks is required to resolve this issue. In this paper, we discuss a novel learning approach that allows to learn a prioritized control law built on a set of sub-tasks represented by motor primitives. The primit...
متن کاملParametric Primitives for Motor Representation and Control
The use of motor primitives for the generation of complex movements is a relatively new and interesting idea for dimensionality reduction in robot control. We propose a framework in which adaptive primitives learn and represent synergetic arm movements. A simple and fixed set of postural and oscillatory primitives form the substrate through which all control is elicited. Higher level adaptive p...
متن کاملAdaptive combination of motor primitives
Recently there has been a growing interest in modeling motor control systems with modular structures. Such control structures have many interesting properties, which have been described in recent studies. We here focus on some properties which are related to the fact that specific set of contexts can themselves be modeled modularly.
متن کاملPolicy Search for Motor Primitives
Many motor skills in humanoid robotics can be learned using parametrized motor primitives from demonstrations. However, most interesting motor learning problems require self-improvement often beyond the reach of current reinforcement learning methods due to the high dimensionality of the state-space. We develop an EM-inspired algorithm applicable to complex motor learning tasks. We compare this...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Proceedings of the National Academy of Sciences
سال: 1994
ISSN: 0027-8424,1091-6490
DOI: 10.1073/pnas.91.16.7534